INDEX

Explanations

actions related to physical manipulation and adjustments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cross

-0.15

 downward

-0.14

ounce

-0.14

SetBranch

-0.14

itect

-0.14

iena

-0.13

á»ĵ

-0.13

ahoo

-0.13

 misd

-0.13

ridor

-0.13

POSITIVE LOGITS

 slightly

0.19

ToFit

0.18

 SHIFT

0.17

ä¸ĢæŃ¥

0.16

olina

0.16

ossier

0.16

èĭ¥

0.16

unes

0.15

Sibling

0.14

à¹īà¸ĩ

0.14

Activations Density 0.153%

actions related to physical manipulation and adjustments

No Comments

No Known Activations

actions related to physical manipulation and adjustments

No Comments

No Known Activations